ADVIS '041 Artificial Life: How can it impact engineering practices of the future? Cihan H. Dagli Smart Engineering Systems Laboratory Engineering Management.

Slides:



Advertisements
Similar presentations
Approaches, Tools, and Applications Islam A. El-Shaarawy Shoubra Faculty of Eng.
Advertisements

A Hybrid IWO/PSO Algorithm for Fast and Global Optimization Hossein Hajimirsadeghi.
Some questions o What are the appropriate control philosophies for Complex Manufacturing systems? Why????Holonic Manufacturing system o Is Object -Oriented.
Security Issues in Ant Routing Weilin Zhong. Outline Swarm Intelligence AntNet Routing Algorithm Security Issues in AntNet Possible Solutions.
Swarm algorithms COMP308. Swarming – The Definition aggregation of similar animals, generally cruising in the same direction Termites swarm to build colonies.
School of Systems, Engineering, University of Reading rkala.99k.org April, 2013 Motion Planning for Multiple Autonomous Vehicles Rahul Kala Literature.
Bio-Inspired Optimization. Our Journey – For the remainder of the course A brief review of classical optimization methods The basics of several stochastic.
Ant Colony Optimization. Brief introduction to ACO Ant colony optimization = ACO. Ants are capable of remarkably efficient discovery of short paths during.
1 Sensor Networks and Networked Societies of Artifacts Jose Rolim University of Geneva.
Chapter 4 DECISION SUPPORT AND ARTIFICIAL INTELLIGENCE
SESSION 10 MANAGING KNOWLEDGE FOR THE DIGITAL FIRM.
Brent Dingle Marco A. Morales Texas A&M University, Spring 2002
Natural Computation and Applications Xin Yao Natural Computation Group School of Computer Science The University of Birmingham.
Evolving Neural Networks in Classification Sunghwan Sohn.
Intelligent Agent Systems. Artificial Intelligence Systems that think like humans Systems that think rationally Systems that act like humans Systems that.
A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra.
1 Hybrid Agent-Based Modeling: Architectures,Analyses and Applications (Stage One) Li, Hailin.
Simulation Models as a Research Method Professor Alexander Settles.
Report WG1 Software-Intensive Systems and New Computing Paradigms Cannes November 12-14, 2008 WG Leader: Martin Wirsing WG Depu ty Leaders: Jean-Pierre.
Building Knowledge-Driven DSS and Mining Data
1 Chapter 19 Intelligent Agents. 2 Chapter 19 Contents (1) l Intelligence l Autonomy l Ability to Learn l Other Agent Properties l Reactive Agents l Utility-Based.
Emergent Phenomena & Human Social Systems NIL KILICAY.
Towards A Multi-Agent System for Network Decision Analysis Jan Dijkstra.
Particle Swarm Optimization Algorithms
Distributed Systems 15. Multiagent systems and swarms Simon Razniewski Faculty of Computer Science Free University of Bozen-Bolzano A.Y. 2014/2015.
SWARM INTELLIGENCE IN DATA MINING Written by Crina Grosan, Ajith Abraham & Monica Chis Presented by Megan Rose Bryant.
Agent Based Modeling and Simulation
Enabling Organization-Decision Making
1 Physical Ensemble Engineering Christof, Heinz, Insup, Seth, Teruo.
By Paul Cottrell, BSc, MBA, ABD. Author Complexity Science, Behavioral Finance, Dynamic Hedging, Financial Statistics, Chaos Theory Proprietary Trader.
4-1 Chapter 4 Decision Support and Artificial Intelligence Brainpower for Your Business.
Chapter 14: Artificial Intelligence Invitation to Computer Science, C++ Version, Third Edition.
Multiple Autonomous Ground/Air Robot Coordination Exploration of AI techniques for implementing incremental learning. Development of a robot controller.
4-1 Management Information Systems for the Information Age Copyright 2004 The McGraw-Hill Companies, Inc. All rights reserved Chapter 4 Decision Support.
Swarm Computing Applications in Software Engineering By Chaitanya.
10/6/2015 1Intelligent Systems and Soft Computing Lecture 0 What is Soft Computing.
Copyright © 2006, The McGraw-Hill Companies, Inc. All rights reserved. Decision Support Systems Chapter 10.
Swarm Intelligence 虞台文.
SWARM INTELLIGENCE Sumesh Kannan Roll No 18. Introduction  Swarm intelligence (SI) is an artificial intelligence technique based around the study of.
Study on Genetic Network Programming (GNP) with Learning and Evolution Hirasawa laboratory, Artificial Intelligence section Information architecture field.
-Abhilash Nayak Regd. No. : CS1(B) “The Power of Simplicity”
(Particle Swarm Optimisation)
Kavita Singh CS-A What is Swarm Intelligence (SI)? “The emergent collective intelligence of groups of simple agents.”
Topics in Artificial Intelligence By Danny Kovach.
FRE 2672 TFG Self-Organization - 01/07/2004 Engineering Self-Organization in MAS Complex adaptive systems using situated MAS Salima Hassas LIRIS-CNRS Lyon.
Chapter 3 DECISION SUPPORT SYSTEMS CONCEPTS, METHODOLOGIES, AND TECHNOLOGIES: AN OVERVIEW Study sub-sections: , 3.12(p )
NAVEEN AGENT BASED SOFTWARE DEVELOPMENT. WHAT IS AN AGENT? A computer system capable of flexible, autonomous (problem-solving) action, situated in dynamic,
Project funded by the Future and Emerging Technologies arm of the IST Programme FET-Open scheme Project funded by the Future and Emerging Technologies.
McGraw-Hill/Irwin ©2008 The McGraw-Hill Companies, All Rights Reserved CHAPTER 9 DECISION MAKING.
Bio-Networking: Biology Inspired Approach for Development of Adaptive Network Applications 21 May 2005Ognen Paunovski Bio-Networking: Biology Inspired.
Neural Networks and Machine Learning Applications CSC 563 Prof. Mohamed Batouche Computer Science Department CCIS – King Saud University Riyadh, Saudi.
Chapter 4 Decision Support System & Artificial Intelligence.
Algorithmic, Game-theoretic and Logical Foundations
Introduction of Intelligent Agents
Technical Seminar Presentation Presented By:- Prasanna Kumar Misra(EI ) Under the guidance of Ms. Suchilipi Nepak Presented By Prasanna.
Distributed Models for Decision Support Jose Cuena & Sascha Ossowski Pesented by: Gal Moshitch & Rica Gonen.
Computational Tools for Population Biology Tanya Berger-Wolf, Computer Science, UIC; Daniel Rubenstein, Ecology and Evolutionary Biology, Princeton; Jared.
Behavior-based Multirobot Architectures. Why Behavior Based Control for Multi-Robot Teams? Multi-Robot control naturally grew out of single robot control.
McGraw-Hill/Irwin © The McGraw-Hill Companies, All Rights Reserved CHAPTER 9 Enabling the Organization—Decision Making.
Artificial Intelligence: Research and Collaborative Possibilities a presentation by: Dr. Ernest L. McDuffie, Assistant Professor Department of Computer.
A field of study that encompasses computational techniques for performing tasks that require intelligence when performed by humans. Simulation of human.
Control-Theoretic Approaches for Dynamic Information Assurance George Vachtsevanos Georgia Tech Working Meeting U. C. Berkeley February 5, 2003.
A Presentation on Adaptive Neuro-Fuzzy Inference System using Particle Swarm Optimization and it’s Application By Sumanta Kundu (En.R.No.
Particle Swarm Optimization (PSO) Algorithm. Swarming – The Definition aggregation of similar animals, generally cruising in the same directionaggregation.
Introduction to Machine Learning, its potential usage in network area,
Intelligent Agents (Ch. 2)
Overview of SWARM INTELLIGENCE and ANT COLONY OPTIMIZATION
Objectives 1. An understanding of the importance of management to society and individuals 2. An understanding of the role of management 3. An ability to.
Objectives 1. An understanding of the importance of management to society and individuals 2. An understanding of the role of management 3. An ability to.
Speaker: Ao Weng Chon Advisor: Kwang-Cheng Chen
Presentation transcript:

ADVIS '041 Artificial Life: How can it impact engineering practices of the future? Cihan H. Dagli Smart Engineering Systems Laboratory Engineering Management Department University of Missouri - Rolla Rolla, MO

ADVIS '042 Presentation Outline Engineering Systems of the Future Engineering Systems of the Future What is Artificial Life? What is Artificial Life? Artificial Life in Engineering Artificial Life in Engineering Concluding Remarks Concluding Remarks

ADVIS '043 Recent Market Changes Total Globalization Total Globalization Increasing Production Pace Increasing Production Pace Decreasing Production Cycle Times Decreasing Production Cycle Times Migration From Mass Production to Mass Customization Migration From Mass Production to Mass Customization

ADVIS '044 Engineering Systems of the Future Immediate Respond to Market Changes Immediate Respond to Market Changes More Sensitive to Customer Needs More Sensitive to Customer Needs Migration from Central to Distributed Control Migration from Central to Distributed Control Autonomous and Cooperating Production Units Autonomous and Cooperating Production Units

ADVIS '045 Smart Systems The term “smart” indicates physical systems that can interact with their environment and adapt to changes through self-awareness and perceived models of the world, based on quantitative and qualitative information. The term “smart” indicates physical systems that can interact with their environment and adapt to changes through self-awareness and perceived models of the world, based on quantitative and qualitative information.

ADVIS '046 Autonomous Units

ADVIS '047 Autonomous Engineered Entity

ADVIS '048 Autonomous Engineered Enterprises

ADVIS '049 Evolutionary Color Images: Karl Sims

ADVIS '0410 Evolutionary Color Images: Karl Sims

ADVIS '0411 “Trajectories” of Research into Distributed Systems System Behavior & Analysis System Design Swarm Intelligence & Synthetic Ecosystems Artificial Life Multi- agent Systems Distributed Artificial Intelligenc e Population Biology& Ecological Modeling

ADVIS '0412 What is Artificial Life? A Perspective: A Perspective: It is a way of imitating Nature in order to solve engineering problems. It is a way of imitating Nature in order to solve engineering problems. It includes simulation and emulation of living systems like plants or animals. It includes simulation and emulation of living systems like plants or animals. It tries to achieve a new understanding of living systems, and of what is life. It tries to achieve a new understanding of living systems, and of what is life.

ADVIS '0413 A Definition: Artificial life is a field of study devoted to understanding life by attempting to abstract the fundamental dynamical principals underlying biological phenomena, and recreating these dynamics in other physical media – such as computers – making them accessible to new kinds of experimental manipulation and testing. (by Christopher G. Langton, from the preface to the Proceedings of the Workshop on Artificial Life, February 1990, Santa Fe, New Mexico) What is Artificial Life?

ADVIS '0414 Adaptive Autonomous Agents Agent: Agent: A system that tries to fulfill a A system that tries to fulfill a set of goals in a complex, dynamic set of goals in a complex, dynamic environment. environment. Environment: Environment: It can sense the environment through It can sense the environment through its sensors and act upon the its sensors and act upon the environment using its actuators. environment using its actuators. Adopted from Modeling Adaptive Autonomous Agents, Pattie Maes

ADVIS '0415 Goal: An agents goal can take many different forms: End Goals, particular states the End Goals, particular states the agent tries to achieve agent tries to achieve Selective reinforcement or reward that the agent attempts to maximize Selective reinforcement or reward that the agent attempts to maximize Internal needs or motivations that the agent has to keep within certain viability zones. Internal needs or motivations that the agent has to keep within certain viability zones. Adopted from Modeling Adaptive Autonomous Agents, Pattie Maes Adaptive Autonomous Agents

ADVIS '0416 Agent Autonomous Autonomous Capable of effective independent action Capable of effective independent action Goal-directed Goal-directed Autonomous actions are directed towards the achievement of defined tasks Autonomous actions are directed towards the achievement of defined tasks Intelligent Intelligent Ability to learn and adapt Ability to learn and adapt Cooperate Cooperate Cooperate with other agents to perform a task Cooperate with other agents to perform a task

ADVIS '0417 Agent Types Cooperate Learn Autonomous Collaborative Learning Agents Smart Agents Interface agents Collaborative Agents

ADVIS '0418 Emergent Phenomena Emergent phenomena are those in which even perfect knowledge and understanding may give us no predictive information. In them the optimal means of prediction is simulation. (Vince Darley, 1994) Emergent phenomena are those in which even perfect knowledge and understanding may give us no predictive information. In them the optimal means of prediction is simulation. (Vince Darley, 1994) The whole is greater than the sum of the parts The whole is greater than the sum of the parts

ADVIS '0419 Artificial Life Techniques Agent-based modeling Agent-based modeling Evolutionary programming Evolutionary programming Genetic algorithms Genetic algorithms Distributed artificial intelligence Distributed artificial intelligence Swarm intelligence Swarm intelligence

ADVIS '0420 Artificial Problem Solvers: Agent-based Modeling Computational method where a system is modeled as a collection of autonomous decision-making entities that interact in non-trivial ways. Computational method where a system is modeled as a collection of autonomous decision-making entities that interact in non-trivial ways. Bottom-up modeling Bottom-up modeling Artificial social systems Artificial social systems

ADVIS '0421 Organizations of agents Animate agents Data Artificial world Observer Inanimate agents If Then Else Courtesy of Lars-Erik Cederman

ADVIS '0422 Areas of Application Flow management: evacuation, traffic, supermarket Flow management: evacuation, traffic, supermarket Markets: stock market, electronic auctions, ISP market Markets: stock market, electronic auctions, ISP market Organizations: operational risk, organizational design Organizations: operational risk, organizational design Diffusion: diffusion of innovation, adoption dynamics Diffusion: diffusion of innovation, adoption dynamics

ADVIS '0423 Flow Management Source:

ADVIS '0424 Exposed Contracts Disease Reports Move Spatially Move Information Agent Location, Demographic & Social Network Characteristics Disease Model Agent Model Daily Community Level Reports Shared BSS Database NEDSS Compliant Geographic Topology Model Environmental Lethality Manifests Symptoms detectionprivacy What If Scenario Impact Analysis Communication Technology Model Courtesy of K. Carley, A. Yahja, B. Kaminsky Artificial BIOWAR

ADVIS '0425 Artificial Problem Solvers: Algorithms Artificial Life tools have led to development of many interesting algorithms that often perform better than classical algorithms within a shorter time. Artificial Life tools have led to development of many interesting algorithms that often perform better than classical algorithms within a shorter time. These algorithms generally contain explicit or implicit parallelism. These algorithms generally contain explicit or implicit parallelism. They resort to distributed agents, or to evolutionary algorithms, or often to both. They resort to distributed agents, or to evolutionary algorithms, or often to both.

ADVIS '0426 Evolving Neural Networks To develop a hybrid intelligent system – Evolving Neural Networks (ENNs) – that can be used in data mining, especially in classification problems. To develop a hybrid intelligent system – Evolving Neural Networks (ENNs) – that can be used in data mining, especially in classification problems.

ADVIS '0427 Evolving Neural Networks Employs computational intelligence methodologies Employs computational intelligence methodologies Neural Networks & Genetic Algorithms Neural Networks & Genetic Algorithms Genetic algorithms have been applied to automatic generation of neural networks Genetic algorithms have been applied to automatic generation of neural networks Feature selection Feature selection Adaptable topology Adaptable topology Customized tasks Customized tasks Ensemble method Ensemble method

ADVIS '0428 Optimizing a NN architecture Using GA

ADVIS '0429 Ensemble of ENNs

ADVIS '0430 Ensemble of ENNs ENNs meet the major requirements of a data mining tool ENNs meet the major requirements of a data mining tool Smart architecture Smart architecture GA  Self-adaptable structure GA  Self-adaptable structure Performance Performance Ensemble method  Accuracy Ensemble method  Accuracy Low complexity  Efficiency Low complexity  Efficiency User interaction User interaction Objective function  Customized classification Objective function  Customized classification

ADVIS '0431 Artificial Problem Solvers: Reinforcement Learning Methods Focus on the rational decision-making process under uncertain environments Focus on the rational decision-making process under uncertain environments Agent can generate a series of actions to influence the evolution of a stochastic dynamic system Agent can generate a series of actions to influence the evolution of a stochastic dynamic system Underlying control problem is often modeled as a Markov Decision Process (MDP). Underlying control problem is often modeled as a Markov Decision Process (MDP).

ADVIS '0432 Reinforcement Learning Methods What to be learned Mapping from situations to actions Mapping from situations to actions Maximizes a scalar reward or reinforcement signal Maximizes a scalar reward or reinforcement signal Learning Does not need to be told which actions to take Does not need to be told which actions to take Must discover which actions yield most reward by trying Must discover which actions yield most reward by trying

ADVIS '0433 Adaptive Critic Design (ACD) The neural control design philosophy The neural control design philosophy Algorithms are intermediate between Direct Reinforcement and Value Function methods, in that the “critic” learns a value function which is then used to update the parameters of the “actor” Algorithms are intermediate between Direct Reinforcement and Value Function methods, in that the “critic” learns a value function which is then used to update the parameters of the “actor”

ADVIS '0434 Need for Online Hybrid Prediction Model Derived from ACD Fundamental drawbacks of supervised learning-based prediction model Fundamental drawbacks of supervised learning-based prediction model Uncertain volatility in real world call for adaptive model Uncertain volatility in real world call for adaptive model Reinforcement learning philosophy is suitable tool especially when the short- time performance of forecasting can be obtained Reinforcement learning philosophy is suitable tool especially when the short- time performance of forecasting can be obtained

ADVIS '0435 Supervised Learning Assisted Reinforcement Learning Prediction Architecture for Time-Series

ADVIS '0436 Stock Price Prediction

ADVIS '0437 Adaptive Model Evolution

ADVIS '0438 Artificial Problem Solvers: Robotics Many robotic systems are currently being developed in the spirit of artificial life. They are devoted to harvesting, mining, ecological sampling etc. Many robotic systems are currently being developed in the spirit of artificial life. They are devoted to harvesting, mining, ecological sampling etc.

ADVIS '0439 Cooperative Behaviour & path Planning for Autonomous Robots Using Evolutionary Algorithm & Fuzzy Clustering

ADVIS '0440 Alice

ADVIS '0441 Artificial Problem Solvers: Evolvable Systems Different categories depending on the complexity and purpose: Different categories depending on the complexity and purpose: Artificial Life Artificial Life Evolvable Hardware (EHW) Evolvable Hardware (EHW) analog analog digital (FPGAs) digital (FPGAs) Hardware design using evolution Hardware design using evolution Evolutionary Robotics Evolving controllers for a purpose Evolutionary Robotics Evolving controllers for a purpose Co-evolution of robot populations Co-evolution of robot populations

ADVIS '0442 Artificial Problem Solvers: Mobile Agents George Cybenko and Bob Gray Thayer School of Engineering Dartmouth College Orders and memos Wireless Network Technical specs Troop positions Wired network

ADVIS '0443 Static & Mobile Agents Developed for Small Unit Operations Courtesy of McGrath et al Objectives: Gather information from sensor reports Gather information from sensor reports Infer additional information from object ontology Infer additional information from object ontology Determine the degree of threat via fuzzy logic inference engine Determine the degree of threat via fuzzy logic inference engine Determine recent nearby alerts using clustering Determine recent nearby alerts using clustering Intelligent “push” of relevant threat data via Grapevine Intelligent “push” of relevant threat data via Grapevine Analysis agent Sensor Field Sensor Report Sent Threat identified and Alert sent Grapevine

ADVIS '0444 George Cybenko and Bob Gray Thayer School of Engineering Dartmouth College Artificial Problem Solvers: Mobile Agents

ADVIS '0445 Multi Agent Co-operative Area Coverage using GA Multi Robot System Multi Robot System Cover Predetermined Area (Go over every square inch) Cover Predetermined Area (Go over every square inch) Boundaries Marked Boundaries Marked Minimize Time and hence Energy Efficient Minimize Time and hence Energy Efficient

ADVIS '0446 Artificial Problem Solvers: Swarm Intelligence “Any attempt to design algorithms or distributed problem-solving devices inspired by the collective behavior of social insect colonies and other animal societies.“ “Any attempt to design algorithms or distributed problem-solving devices inspired by the collective behavior of social insect colonies and other animal societies.“ -[Bonabeau et al., 1999]-

ADVIS '0447 Swarming Characteristics Entities share common goal Local Interaction s Self Organizatio n Autonomy of units Stigmergy Simple rules or units Distribute d Large number or efficient size Pulsing of force Flexible and robust Swarming

ADVIS '0448 Emergent- Self assembled Nest Courtesy of Bonabeau

ADVIS '0449 Ant Colony Optimization 1. Straight Pheromone Trail2. Obstacle Introduced 3. Two Options are Explored 4. Shortest Path Dominates

ADVIS '0450 Routing in Communication Networks

ADVIS '0451 Future Combat Systems Courtesy of Riggs J.

ADVIS '0452 Particle Swarm Optimization Original intent was to simulate the choreography of a bird flock Best strategy to find the food is to follow the bird which is nearest to the food

ADVIS '0453 PSO Initialization: Positions and velocities Courtesy of Maurice Clerk

ADVIS '0454 Particle Swarm Optimization Global optimum Courtesy of Maurice Clerk The best solution (fitness) particle has achieved so far (pbest) The best value obtained so far by any particle in the population (gbest)

ADVIS '0455 Artificial Problem Solvers: Synthetic Ecosystems The synthetic ecosystems approach applies swarm intelligence to the design of multi-agent systems. The synthetic ecosystems approach applies swarm intelligence to the design of multi-agent systems. The main concern of research into synthetic ecosystems is to provide practical engineering guidelines to design systems of industrial strength The main concern of research into synthetic ecosystems is to provide practical engineering guidelines to design systems of industrial strength [Parunak, 1997] [Parunak et al., 1998]

ADVIS '0456 Distributed Architectures for Manufacturing Holonic Systems Holonic Systems A whole individual and a part at the same time A whole individual and a part at the same time “An autonomous and cooperative building block of a manufacturing system for transforming, transporting, storing and/or validating information and physical objects” “An autonomous and cooperative building block of a manufacturing system for transforming, transporting, storing and/or validating information and physical objects” [Christensen, 1994] A manufacturing holon comprises a control part and an optional physical processing part. Multiple holons may dynamically aggregate into a single (higher-level) holon. A manufacturing holon comprises a control part and an optional physical processing part. Multiple holons may dynamically aggregate into a single (higher-level) holon.

ADVIS '0457 Distributed Architectures for Manufacturing The application of the holonic concept to the manufacturing domain is expected to yield systems of autonomous, cooperating entities that self-organize to achieve the current production goals. The application of the holonic concept to the manufacturing domain is expected to yield systems of autonomous, cooperating entities that self-organize to achieve the current production goals. Such systems meet the requirements of tomorrow's manufacturing control systems. Such systems meet the requirements of tomorrow's manufacturing control systems.

ADVIS '0458 Concluding Remarks Artificial Life is impacting engineering systems through Agent-Based architectures Artificial Life is impacting engineering systems through Agent-Based architectures Current Impact Areas: Current Impact Areas: Enterprise Integration and Supply Chain Management Enterprise Integration and Supply Chain Management Design and Manufacturability Assessments Design and Manufacturability Assessments Enterprise Planning, Scheduling and Control Enterprise Planning, Scheduling and Control

ADVIS '0459 Current Impact Areas: Current Impact Areas: Dynamic System Reconfiguration Dynamic System Reconfiguration Factory Control Architectures Factory Control Architectures Holonic Manufacturing Systems Holonic Manufacturing Systems Distributed Dynamic Scheduling Distributed Dynamic Scheduling Commercial scheduling, routing, and force allocation problems Commercial scheduling, routing, and force allocation problems Use of swarm networks to control swarm Unmanned Aerial Vehicles (UAV), or undersea vehicles (UGV) Use of swarm networks to control swarm Unmanned Aerial Vehicles (UAV), or undersea vehicles (UGV) Concluding Remarks